no code implementations • Findings (ACL) 2022 • Jinfa Yang, Xianghua Ying, Yongjie Shi, Xin Tong, Ruibin Wang, Taiyan Chen, Bowei Xing
The recently proposed Limit-based Scoring Loss independently limits the range of positive and negative triplet scores.
1 code implementation • COLING 2022 • Jinfa Yang, Xianghua Ying, Yongjie Shi, Xin Tong, Ruibin Wang, Taiyan Chen, Bowei Xing
It is crucial for knowledge graph embedding models to model and infer various relation patterns, such as symmetry/antisymmetry.
no code implementations • CVPR 2022 • Xin Tong, Xianghua Ying, Yongjie Shi, Ruibin Wang, Jinfa Yang
To achieve this goal, we propose a novel Transformer based Line segment Classifier (TLC) that can group line segments in images and estimate the corresponding vanishing points.